agent-skills: Instructions file for Claude Code

CLAUDE.md

agent-skills CLAUDE.md is an instructions file for Claude Code from Osipchuk/agent-skills. It costs 2,329 tokens per session, scanned A, original, MIT.

A set of working rules for Claude Code in a software repository. It tells the coding agent to think through the task, keep solutions simple, and make only the necessary code changes.

In plain words
What is it for?
Use it to guide code changes, especially when a task has several possible interpretations or could be solved in more than one way.
Why use it?
It helps prevent unnecessary rewrites, speculative features, and changes to unrelated files. It also encourages the agent to surface unclear requirements before coding.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Osipchuk/agent-skills's own configuration. It tells Claude Code how to work on agent-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Osipchuk/agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Osipchuk/agent-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Osipchuk/agent-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/osipchuk/agent-skills/claude-md.svg)](https://agentmods.dev/instructions/osipchuk/agent-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/osipchuk/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/osipchuk/agent-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,329 This file is loaded in full into every session.
When invoked 2,329 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02329 $0.02329
Opus 5 $0.01164 $0.01164
Sonnet 5 $0.00466 $0.00466
Haiku 4.5 $0.00233 $0.00233

Measured 7d ago against content hash 20a9be25dd08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-skills CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Two install tracks.** Humans: `install.sh` (uvx/`uv tool install` from git). The agent path: the Claude Code plugin marketplace (`.claude-plugin/marketplace.json` → `/plugin install skills@askill`), which is the trus
CLAUDE.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working in this repo: how to work here first, then how the project is built. The working principles are adapted from Andrej Karpathy's skills CLAUDE.md (multica-ai/andrej-karpathy-skills); merge with anything more specific a task demands.

Tradeoff: these principles bias toward caution over speed. For a trivial task, use judgment.

Working principles

1. Think before coding

Don't assume, don't hide confusion, surface tradeoffs. State your assumptions; if several readings are possible, present them instead of silently picking one. If a simpler path exists, say so. If something is unclear, stop and name it — a clarifying question before the work beats a rewrite after it.

2. Simplicity first

Minimum code that solves the problem, nothing speculative. No abstraction for a single caller, no configurability nobody asked for, no error handling for impossible states. This repo already has a small, clean deterministic core — match that bar, don't gold-plate past it. If you wrote 200 lines and 50 would do, rewrite it.

3. Surgical changes

Touch only what the task needs. Don't "improve" adjacent code, comments, or formatting; don't refactor what isn't broken; match the surrounding style even if you'd write it differently. Remove only the imports/vars/functions your change orphaned — flag pre-existing dead code, don't delete it unasked. Every changed line should trace to the request.

4. Verify, don't assert

Turn the task into a check and loop until it passes. "Fix the bug" → write the failing test first, then make it pass. Before claiming done, actually run it: uv run pytest && uv run ruff check . && uv run mypy src from installer/. Generated artifacts (below) have their own check — regenerate and diff, don't eyeball.

Two repo-specific habits fall out of these:

  • The deterministic Core is the product. Keep logic pure in core/; isolate side effects (I/O, network, prompts) at the edges. cli.py/commands/ only parse args and call Core; the human-vs-JSON decision lives in utils/output.py, not in commands.
  • Generated files are never hand-edited. Change the generator, run it, commit the output — see "Generated artifacts" below.

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 94 lines · 2,329 tokens per session scan A 20a9be25dd08

Subscribe to this mod's changes

agent-skills CLAUDE.md is an instructions file published in the GitHub repository Osipchuk/agent-skills (5 stars, last pushed 27d ago), licensed MIT. It adds 2,329 tokens to every session, about $0.0116 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens